# Composite Correlation Quantization for Efficient Multimodal Retrieval

arXiv: https://arxiv.org/abs/1504.04818 · HTML: https://mlsanity.com/paper/1504.04818/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2015.

## Built on by (most cited first, 6 of 6)

- [Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.01195/) (2022)
- [FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal Retrieval](https://mlsanity.com/paper/2105.07128/) (2021)
- [MOON: Multi-Hash Codes Joint Learning for Cross-Media Retrieval](https://mlsanity.com/paper/2109.00883/) (2021)
- [Efficient Cross-Modal Retrieval via Deep Binary Hashing and Quantization](https://mlsanity.com/paper/2202.10232/) (2022)
- [Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation](https://mlsanity.com/paper/2306.13420/) (2023)
- [Distilling Vision-Language Pretraining for Efficient Cross-Modal Retrieval](https://mlsanity.com/paper/2405.14726/) (2024)

## Abstract (arXiv)

Efficient similarity retrieval from large-scale multimodal database is pervasive in modern search engines and social networks. To support queries across content modalities, the system should enable cross-modal correlation and computation-efficient indexing. While hashing methods have shown great potential in achieving this goal, current attempts generally fail to learn isomorphic hash codes in a seamless scheme, that is, they embed multiple modalities in a continuous isomorphic space and separately threshold embeddings into binary codes, which incurs substantial loss of retrieval accuracy. In this paper, we approach seamless multimodal hashing by proposing a novel Composite Correlation Quantization (CCQ) model. Specifically, CCQ jointly finds correlation-maximal mappings that transform different modalities into isomorphic latent space, and learns composite quantizers that convert the isomorphic latent features into compact binary codes. An optimization framework is devised to preserve both intra-modal similarity and inter-modal correlation through minimizing both reconstruction and quantization errors, which can be trained from both paired and partially paired data in linear time. A comprehensive set of experiments clearly show the superior effectiveness and efficiency of CCQ against the state of the art hashing methods for both unimodal and cross-modal retrieval.